DeepSeek V3.2 Thinking
DeepSeek V3.2 Thinking is DeepSeek's language model with a 128K context window and up to 64K output tokens, starting at $0.280 / 1M input and $0.420 / 1M output. A thinking-mode variant of DeepSeek V3.2 that enables explicit chain-of-thought reasoning with tool-use support and implicit caching.
DeepSeek's language model with a 128K context window and up to 64K output tokens, starting at $0.280 / 1M input and $0.420 / 1M output. A thinking-mode variant of DeepSeek V3.2 that enables explicit chain-of-thought reasoning with tool-use support and implicit caching.Capabilities
Input1/5
✓
·
·
·
·
Output1/5
✓
·
·
·
·
Capabilities3/13
✓
·
✓
·
·
·
·
·
·
·
·
✓
·
Pricing by Provider
| Provider | Standard | ||
|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | |
 Vercel AI Gateway | $0.280 | $0.420 | $0.028 |
Cost Calculator
Preset:
Compares every provider & tier in USD
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| DeepSeek V3.2 Thinking | 128K | $0.280 | $0.420 | Current | |
| DeepSeek V3.2 | 164K | $0.259 | $0.400 | Available | |
| DeepSeek V3.2 Speciale | 164K | $0.400 | $1.20 | Available | |
| DeepSeek V3.2 Exp | 164K | $0.270 | $0.410 | Available | |
| DeepSeek V3.2 Exp | — | — | — | — | Available |
| DeepSeek V3.2 Exp | — | — | — | — | Available |
| DeepSeek V3.1 Nex N1 | 131K | — | — | Available | |
| DeepSeek V3.1 Terminus | 164K | $0.210 | $0.790 | Available | |
| DeepSeek V3.1 | 164K | $0.150 | $0.750 | Available | |
| DeepSeek V3.1 671B | — | 164K | — | — | Available |
| DeepSeek V3 | 164K | $0.200 | $0.200 | Available |